Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2273 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.0823. Min Act: -0.0001

Data Index: 397335 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.1160. Min Range: -1.1160

Max Act: 1.1160. Min Act: -0.0001

Data Index: 114145 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9867. Min Act: -0.0001

Data Index: 910342 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9731. Min Act: -0.0001

Data Index: 664451 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9706. Min Act: -0.0001

Data Index: 950222 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9284. Min Act: -0.0001

Data Index: 903083 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9547. Min Act: -0.0001

Data Index: 399669 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9175. Min Act: -0.0001

Data Index: 746077 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8962. Min Act: -0.0001

Data Index: 188353 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9206. Min Act: -0.0001

Data Index: 921010 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9651. Min Act: -0.0001

Data Index: 161618 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9200. Min Act: -0.0001

Data Index: 24578 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9422. Min Act: -0.0001

Data Index: 142633 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9078. Min Act: -0.0001

Data Index: 1354081 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9107. Min Act: -0.0001

Data Index: 717137 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.9827. Min Act: -0.0001

Data Index: 828694 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8962. Min Act: -0.0001

Data Index: 1255565 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8951. Min Act: -0.0001

Data Index: 1132489 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8895. Min Act: -0.0001

Data Index: 1129914 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 1.1160. Min Range: -1.1160

Max Act: 0.8873. Min Act: -0.0001

Data Index: 452567 (C4 (Web Text))

Max Activating Token Index: 237